Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add HiAgencia/hi-claude/plugin install hi-claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hiagencia/hi-claude/memory-protocol)<a href="https://agentmods.dev/skills/hiagencia/hi-claude/memory-protocol"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/memory-protocol/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hiagencia/hi-claude/memory-protocol"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/memory-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00154 | $0.00973 |
| Opus 5 | $0.00077 | $0.00487 |
| Sonnet 5 | $0.00031 | $0.00195 |
| Haiku 4.5 | $0.00015 | $0.00097 |
Grade A, and why
memory-protocol scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Protocol (hi-claude)
Decide whether a piece of knowledge deserves persistence, where it goes, and write it in the canonical format — always with user approval.
Workflow
- Classify against the ADMISSION axis. The Constitution defines the seven principles and their four axes, and is normally already in context; if it is not (the session hook could not run), read
${CLAUDE_PLUGIN_ROOT}/skills/memory-protocol/constitution.md. If the candidate does not qualify → do NOT persist; say nothing unless asked. If it is documentation or a procedure → offer to put it indocs/and reference the path from CLAUDE.md instead. Then write it under the WRITING axis, which is a separate question: what passes admission still has to be OBJECTIVE (the fact with its evidence, no attributed cause, no verdict of value) and NON-CONDITIONING (the state observed with its method and its N, never a closed door). A memory that says something cannot be done costs every future session the attempt — and a memory is exactly the text that outlives the reason it was written. - Check scope. If the preference applies to ALL of the user's projects (not just this one), propose saving it ONCE at user level (
~/.claude/CLAUDE.mdor~/.claude/rules/) instead of duplicating per-project memories. - Choose the destination using
references/decision-tree.md. For memory entries, choose the type:user— who the user is: role, expertise, how they like to receive outputfeedback— corrections ("don't do X") and validated approaches ("yes, exactly like that")project— decisions, priorities, context not in the codereference— pointers to external systems (URLs, boards, dashboards)
- Draft the entry in the EXACT format defined in
references/memory-schema.md. Read that file before writing your first memory of the session. - Propose, then wait. Show the user (in their language): target filename, type, and the full content. Ask for approval. NEVER write without it — a PreToolUse guard will force confirmation anyway.
- Write + index. On approval: write the file, then add one line to
MEMORY.md. Keep the index under 200 lines (it truncates silently beyond that); when it passes ~150 lines, propose consolidation first. - Replacements. If the new knowledge corrects an existing memory, write
Replaces obsolete memory: [[old-name]]in the body and propose deleting the old file in the same approval.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 43 lines · 154 tokens per session scan A 760f1a8f26e3
memory-protocol is a skill published in the GitHub repository HiAgencia/hi-claude (2 stars, last pushed 18d ago), licensed MIT. It adds 154 tokens to every session and 973 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.